Evaluating the legacy of landscape history: extinction debt and species credit in bird and small mammal assemblages in the Brazilian Atlantic Forest

There is now an extensive literature on extinction debt following deforestation. However, the potential for species credit in landscapes that have experienced a change from decreasing to expanding forest cover has received little attention. Both delayed responses should depend on current landscape forest cover and on species life-history traits, such as longevity, as short-lived species are likely to respond faster than long-lived species. We evaluated the effects of historical and present-day local forest cover on two vertebrate groups with different longevities understorey birds and non-flying small mammals - in forest patches at three Atlantic Forest landscapes. Our work investigated how the probability of extinction debt and species credit varies (i) amongst landscapes with different proportions of forest cover and distinct trajectories of forest cover change, and (ii) between taxa with different life spans. Our results suggest that the existence of extinction debt and species credit, as well as the potential for their future payment and/or receipt, is not only related to forest cover trajectory but also to the amount of remaining forest cover at the landscape scale. Moreover, differences in bird and small mammal life spans seem to be insufficient to affect differently their probability of showing time-delayed responses to landscape change. Synthesis and applications. Our work highlights the need for considering not only the trajectory of deforestation/regeneration but also the amount of forest cover at landscape scale when investigating time-delayed responses to landscape change. As many landscapes are experiencing a change from decreasing to expanding forest cover, understanding the association of extinction and immigration processes, as well as their interactions with the landscape dynamic, is a key factor to plan conservation and restoration actions in human-altered landscapes.

On the impact of disproportional samples in credit scoring models: An application to a Brazilian bank data

Statistical methods have been widely employed to assess the capabilities of credit scoring classification models in order to reduce the risk of wrong decisions when granting credit facilities to clients. The predictive quality of a classification model can be evaluated based on measures such as sensitivity, specificity, predictive values, accuracy, correlation coefficients and information theoretical measures, such as relative entropy and mutual information. In this paper we analyze the performance of a naive logistic regression model (Hosmer & Lemeshow, 1989) and a logistic regression with state-dependent sample selection model (Cramer, 2004) applied to simulated data. Also, as a case study, the methodology is illustrated on a data set extracted from a Brazilian bank portfolio. Our simulation results so far revealed that there is no statistically significant difference in terms of predictive capacity between the naive logistic regression models and the logistic regression with state-dependent sample selection models. However, there is strong difference between the distributions of the estimated default probabilities from these two statistical modeling techniques, with the naive logistic regression models always underestimating such probabilities, particularly in the presence of balanced samples. (C) 2012 Elsevier Ltd. All rights reserved.